CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA
Transparent educational question answering asks for answers that are not only correct but explainable, and doing so with small models rules out the reasoning power of the largest proprietary systems. The EXACT 2026 competition poses this problem concretely: open-weight language models of at most 8B parameters, self-hosted, with a natural-language explanation for every answer. It pairs two tasks: logical reasoning over university regulations, and multi-step physics problem solving. We describe the system that team \cotu{} developed to address both, a neuro-symbolic Program-of-Thought pipeline i
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Northwind AI →
- FuzzyOverlapping authors or contributors · 62%ultralytics/yolov5 →
“Shared author/contributor keys: tran”
- FuzzyOverlapping authors or contributors · 62%open-webui/open-webui →
“Shared author/contributor keys: nguyen”
- FuzzySimilar title/name (fuzzy) · 59%rasbt/reasoning-from-scratch →
“Fuzzy title match (0.73): “CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent” ≈ “rasbt/reasoning-from-scratch””
- LinkedLinked via arxiv author · 85%Quoc-Khang Tran →
“CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA”
- LinkedLinked via arxiv author · 85%Minh-Thien Nguyen →
“CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA”
- LinkedLinked via arxiv author · 85%Phu-An Thai →
“CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA”
- LinkedLinked via arxiv author · 85%Xuan-Tung Bui →
“CoTu at EXACT 2026: Neuro-Symbolic Reasoning for Transparent Educational QA”